© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 122162
    Prev
    Next
    INDEX
    Explanations

    local business

    np_acts-logits-general · gemini-2.5-flash-lite

    write, harm, burns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ብዙውን
    0.54
     평
    0.54
     者
    0.51
     मठ
    0.50
     先
    0.49
    cription
    0.48
     自分
    0.48
     ちゃん
    0.47
    மைக்
    0.47
     こう
    0.46
    POSITIVE LOGITS
    dN
    0.50
    ன
    0.49
    قی
    0.49
    )~
    0.48
    См
    0.46
    рті
    0.45
    Aurora
    0.45
    Eugene
    0.44
     august
    0.44
    winfx
    0.43
    Activations Density 0.000%

    No Known Activations